Dean Giberson deangiberson

Minimal Prompt Chainables

Sequential prompt chaining in one method with context and output back-referencing.

Files

main.py - start here - full example using MinimalChainable from chain.py to build a sequential prompt chain
chain.py - contains zero library minimal prompt chain class
chain_test.py - tests for chain.py, you can ignore this
requirements.py - python requirements

Setup

You probably don't know how to do Prompt Engineering

(This post could also be titled "Features missing from most LLM front-ends that should exist")

Apologies for the snarky title, but there has been a huge amount of discussion around so called "Prompt Engineering" these past few months on all kinds of platforms. Much of it is coming from individuals who are peddling around an awful lot of "Prompting" and very little "Engineering".

Most of these discussions are little more than users finding that writing more creative and complicated prompts can help them solve a task that a more simple prompt was unable to help with. I claim this is not Prompt Engineering. This is not to say that crafting good prompts is not a difficult task, but it does not involve doing any kind of sophisticated modifications to general "template" of a prompt.

Others, who I think do deserve to call themselves "Prompt Engineers" (and an awful lot more than that), have been writing about and utilizing the rich new eco-system

Rails Rspec APIs Testing Notes

Folders Structure

  spec
  |--- apis #do not put into controllers folder. 
        |--- your_api_test_spec.rb  
  |--- controllers
  |--- models
  |--- factories
 |--- views

The Scope class regulates lexical scoping within CoffeeScript. As you generate code, you create a tree of scopes in the same shape as the nested function bodies. Each scope knows about the variables declared within it, and has a reference to its parent enclosing scope. In this way, we know which variables are new and need to be declared with var, and which are shared with the outside.

Import the helpers we plan to use.

{extend, last} = require './helpers'

	# If you, like me, have all of your various source-code-like projects in ~/src/
	# this is how to give yourself per-project shell history.
	#
	# I wish I'd done this years ago.
	#
	# First, in your .bashrc file, you redefine the cd, pushd and popd builtins to be "do the builtin bit,
	# then do one other thing (set_src_history.sh, below) like so:


	cd () {

	(ns lenskit-hello.core
	(:require [clojure.java.io :as io])
	(:import [org.grouplens.lenskit
	ItemRecommender ItemScorer Recommender RecommenderBuildException]
	[org.grouplens.lenskit.baseline
	BaselineScorer ItemMeanRatingItemScorer UserMeanBaseline
	UserMeanItemScorer]
	[org.grouplens.lenskit.core
	LenskitConfiguration LenskitRecommender]
	[org.grouplens.lenskit.cursors Cursors]

	# First attempting to use Capybara directly, you will ran into issues when trying to set HTTP header.
	# Using Basic HTTP Authentication requires that we needed to set the header.
	# Also we need to set the Content-Type and Accept headers to ensure that Rails handles the input and output correctly.
	# When using Rack, Capybara delegates request and response handling down to Rack::Test.
	# So I used Rack::Test directly in my step definitions, and it works.
	# Rack::Test has a module called Rack::Test::Methods that can be mixed into a class to provide it
	# with methods for get, post, put, delete as well as last_request, last_response, header and more.
	# I mixed Rack::Test::Methods into the Cucumber world at the top of our API steps file like so:

	##############################

	; A REPL-based, annotated Seesaw tutorial
	; Please visit https://github.com/daveray/seesaw for more info
	;
	; This is a very basic intro to Seesaw, a Clojure UI toolkit. It covers
	; Seesaw's basic features and philosophy, but only scratches the surface
	; of what's available. It only assumes knowledge of Clojure. No Swing or
	; Java experience is needed.
	;
	; This material was first presented in a talk at @CraftsmanGuild in
	; Ann Arbor, MI.